Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1]  54  49 578 113 919 489 915 367 344 180  63 270 900 281 553 320 778 358 717 331
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 331 180  49 915 578 919 900 717 113 358  NA 344 367 778 553 320  63 489 270  NA  NA  54 281
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 2 3 1 3 1 4 3 2 5 4
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "t" "e" "j" "p" "v" "L" "C" "U" "X" "D"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 5 7
which( manyNumbersWithNA > 900 )
[1] 4 6
which( is.na( manyNumbersWithNA ) )
[1] 11 20 21

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 919 915
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 919 915
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 919 915

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "L" "C" "U" "X" "D"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "t" "e" "j" "p" "v"
manyNumbers %in% 300:600
 [1] FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE
[18]  TRUE FALSE  TRUE
which( manyNumbers %in% 300:600 )
[1]  3  6  8  9 15 16 18 20
sum( manyNumbers %in% 300:600 )
[1] 8

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "small" "small" "large" "large" "large" "large" "large" "small" "small" NA      "small" "small"
[14] "large" "large" "small" "small" "small" "small" NA      NA      "small" "small"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "small"   "small"   "large"   "large"   "large"   "large"   "large"   "small"   "small"  
[11] "UNKNOWN" "small"   "small"   "large"   "large"   "small"   "small"   "small"   "small"   "UNKNOWN"
[21] "UNKNOWN" "small"   "small"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0   0   0 915 578 919 900 717   0   0  NA   0   0 778 553   0   0   0   0  NA  NA   0   0

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 2 3 1 4 5
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  2  3  1  4  5
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE  TRUE FALSE  TRUE  TRUE FALSE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 6
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 919
which.min( manyNumbersWithNA )
[1] 3
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 49
range( manyNumbersWithNA, na.rm = TRUE )
[1]  49 919

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 331 180  49 915 578 919 900 717 113 358  NA 344 367 778 553 320  63 489 270  NA  NA  54 281
sort( manyNumbersWithNA )
 [1]  49  54  63 113 180 270 281 320 331 344 358 367 489 553 578 717 778 900 915 919
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  49  54  63 113 180 270 281 320 331 344 358 367 489 553 578 717 778 900 915 919  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 919 915 900 778 717 578 553 489 367 358 344 331 320 281 270 180 113  63  54  49  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 331 180  49 915 578
order( manyNumbersWithNA[1:5] )
[1] 3 2 1 5 4
rank( manyNumbersWithNA[1:5] )
[1] 3 2 1 5 4
sort( mixedLetters )
 [1] "C" "D" "e" "j" "L" "p" "t" "U" "v" "X"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 1.0 7.0 3.5 3.5 7.0 3.5 9.5 7.0 3.5 9.5
rank( manyDuplicates, ties.method = "min" )
 [1] 1 6 2 2 6 2 9 6 2 9
rank( manyDuplicates, ties.method = "random" )
 [1]  1  7  5  4  6  2 10  8  3  9

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000 -0.67396428 -0.13518803 -0.76440720
 [9] -0.96543267 -0.36329583 -0.98591783  0.44122914  0.06678965 -0.15158257 -0.84128778
round( v, 0 )
 [1] -1  0  0  0  1 -1  0 -1 -1  0 -1  0  0  0 -1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.7 -0.1 -0.8 -1.0 -0.4 -1.0  0.4  0.1 -0.2 -0.8
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.67 -0.14 -0.76 -0.97 -0.36 -0.99  0.44  0.07 -0.15 -0.84
floor( v )
 [1] -1 -1  0  0  1 -1 -1 -1 -1 -1 -1  0  0 -1 -1
ceiling( v )
 [1] -1  0  0  1  1  0  0  0  0  0  0  1  1  0  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC